[R-sig-eco] Time series and GLS

[Nicholas Lewin-Koh]

Hi Lisa,
The point of including time in the model is that your data are
ordered in time. If there is reason to believe that food availability 
at year t has no influence on food availability in year t + 1 
than all you need is success~food. But alas ecology is rarely that
simple
and I would guess that to relate the series you need to model the
auto-correlation,
so something like gls(success~food, corr = corAR1(form = ~ yr)). And of
course that can be extended to
a gam. Also if you run into non-stationarity you might try differencing
your series
ie delta(success)~delta(food). 

Nicholas



> 
> Message: 1
> Date: Mon, 4 Jan 2010 14:05:25 -0800 (PST)
> From: LisaB <lisabaril at hotmail.com>
> Subject: Re: [R-sig-eco] Time series and GLS
> To: r-sig-ecology at r-project.org
> Message-ID: <1262642725636-4252318.post at n2.nabble.com>
> Content-Type: text/plain; charset=us-ascii
> 
> 
> Thanks for the very helpful advice.  I've been doing a lot of plotting
> and it
> looks like portions of my time series are linearly related with year, but
> there are clear deviations from this so I've also been looking at using
> gam
> with smoothers, but still have a ways to go before settling on a model
> that
> adequately describes the data.  After describing trends over time for
> nest
> success, I'll eventually want to relate nest success with food
> availability
> (also a time series variable).  Both nest success and food availability
> generally decline over time in a similar way.  Since year and food
> availability are correlated and I probably should not use them in the
> same
> model to describe nest success, but I still need to control for year
> -correct?  Is it valid to specify the general model as: nest success~food
> availability+error even though both the response and explanatory
> variables
> are negatively correlated with time?  I ask because in the "Mixed models
> and
> extensions in R" book, chapter 14 describes a similar problem in which
> they
> leave out year in a model where the explanatory variable exhibited a
> trend
> over time.  However, in other sources I read that this could be a major
> problem.  Sorry for the rather long-winded question.  I'm new to time
> series
> analysis.  Thanks to anyone who can provide some insight.   
> 
> 
> 
> 
> LisaB wrote:
> > 
> > Hello -
> > 
> > I need to analyze some time series data in an ANOVA framework, but am
> > unsure of how to go about it.  I have data on nest success (response) over
> > a 22 year period for two populations.  For each year I have one value of
> > nest success per population.  I am interested in determining 1) whether
> > there are differences in nest success over time between these two
> > populations and 2) what are the trends for each population over time.  My
> > thought is to use GLS and model temporal autocorrelation if the acf
> > function indicates this is an issue, but since population is a categorical
> > variable I'm unsure if this is appropriate.  Any advice would be much
> > appreciated. Thank you. Lisa
> > 
> > 
> > 
> >    
> > 
> 
> -- 
> View this message in context:
> http://n2.nabble.com/Time-series-and-GLS-tp4240700p4252318.html
> Sent from the r-sig-ecology mailing list archive at Nabble.com.
> 
> 
>